<br><br><div class="gmail_quote">On Mon, Feb 4, 2013 at 9:14 AM, Kushnir, Michael (NIH/NLM/LHC) [C] <span dir="ltr"><<a href="mailto:michael.kushnir@nih.gov" target="_blank">michael.kushnir@nih.gov</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
<div lang="EN-US" link="blue" vlink="purple">
<div>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri","sans-serif";color:#1f497d">Hi All,
<u></u><u></u></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri","sans-serif";color:#1f497d"><u></u> <u></u></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri","sans-serif";color:#1f497d">I have a couple small compute clusters set up as clients to GlusterFS volumes mounted over fuse. My GlusterFS servers are separate and independent of these
compute clusters. <u></u><u></u></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri","sans-serif";color:#1f497d"><u></u> <u></u></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri","sans-serif";color:#1f497d">Are the IO Wait figures that I see in top on the GlusterFS clients accurate and inclusive of the GlusterFS, or should I be looking somewhere else to check for
client side IO bottlenecks relating to GlusterFS fuse mounts?<u></u><u></u></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri","sans-serif";color:#1f497d"><br>
Thanks,<br>
Michael <u></u><u></u></span></p>
</div>
</div>
</blockquote></div><br><div>IIRC it should include client side IO delays. It would be best to ask this question on fuse-devel@ list.</div><div><br></div><div>Avati</div>